mlsanityData to 7 Oct 2026

Benchmarking Multi-Domain Active Learning on Image Classification

arXiv 2312.00364 ↗First posted 1 Dec 2023cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Active learning aims to enhance model performance by strategically labeling informative data points. While extensively studied, its effectiveness on large-scale, real-world datasets remains underexplored. Existing research primarily focuses on single-source data, ignoring the multi-domain nature of real-world data. We introduce a multi-domain active learning benchmark to bridge this gap. Our benchmark demonstrates that traditional single-domain active learning strategies are often less effective than random selection in multi-domain scenarios. We also introduce CLIP-GeoYFCC, a novel large-scale image dataset built around geographical domains, in contrast to existing genre-based domain datasets. Analysis on our benchmark shows that all multi-domain strategies exhibit significant tradeoffs, with no strategy outperforming across all datasets or all metrics, emphasizing the need for future research.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

25 of 40 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  4. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  6. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  7. 2020A Survey of Deep Active Learningcited by 547
  8. 2015Learning Multi-Domain Convolutional Neural Networks for Visual Trackingcited by 209
  9. 2016What makes ImageNet good for transfer learning?cited by 192
  10. 2020Minimax Pareto Fairness: A Multi Objective Perspectivecited by 152
  11. 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performancecited by 141
  12. 2021Batch Active Learning at Scalecited by 127
13 more
  1. 2019Active Adversarial Domain Adaptationcited by 73
  2. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  3. 2021Adaptive Methods for Real-World Domain Generalizationcited by 66
  4. 2018Multinomial Adversarial Networks for Multi-Domain Text Classificationcited by 40
  5. 2020Active Sampling for Min-Max Fairnesscited by 33
  6. 2022Active Learning Helps Pretrained Models Learn the Intended Taskcited by 33
  7. 2020Fair Active Learningcited by 30
  8. 2021Adaptive Sampling for Minimax Fair Classificationcited by 24
  9. 2021Conditional Adversarial Networks for Multi-Domain Text Classificationcited by 16
  10. 2018On the Relationship between Data Efficiency and Error for Uncertainty Samplingcited by 12
  11. 2020On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Taskscited by 10
  12. 2022Is margin all you need? An extensive empirical study of active learning on tabular datacited by 10
  13. 2021Multi-Domain Active Learning: Literature Review and Comparative Studycited by 6

Built on by

Not cited yet.